AI Paper Atlas

Research map / Optimization / Optimizers

Training Neural Networks for and by Interpolation

Leonard Berrada, Andrew Zisserman, M. Pawan Kumar

ICML 2020 · Optimization › Optimizers · approach: Memory-efficient LLM optimizers · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use ALI-G instead of AdamBi-LSTM · SNLI test, cross-entropyaccuracy: 84.5 -> 84.8Improved
Use ALI-G instead of DFWBi-LSTM · SNLI test, SVMaccuracy: 85.2 -> 85.2No clear effect
Use ALI-G instead of scheduled SGDWRN 16-4 · SVHN testaccuracy: 98.3 -> 98.1Hurt
Use ALI-G instead of scheduled SGDWRN 40-4 · CIFAR-10 testaccuracy: 95.3 -> 95.2Hurt
Use ALI-G instead of scheduled SGDDN 40-40 · CIFAR-10 testaccuracy: 95.1 -> 95.0Hurt
Use ALI-G instead of DFWWRN 40-4 · CIFAR-100 testaccuracy: 76.0 -> 75.8Hurt
Use ALI-G instead of scheduled SGDDN 40-40 · CIFAR-100 testaccuracy: 76.3 -> 76.3No clear effect
Remove the maximal learning-rate cap (ablation)ALI-G on Bi-LSTM · SNLI test, cross-entropyaccuracy: 84.8 -> 84.6No clear effect
Remove the maximal learning-rate cap (ablation)ALI-G on Bi-LSTM · SNLI test, SVMaccuracy: 85.2 -> 84.7No clear effect
Replace the capped ALI-G step with an uncapped step (ablation)ALI-G on an RSI non-convex problem · Non-convex convergence exampleconvergenceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy